机器学习-KNN图像分类

步骤：
（1）：计算测试数据与训练数据之间的距离；
（2）：按结果距离排序
（3）：选取距离最小的K个点
（4）：确定此K个样本中各个类别的频率
（5）：将频率最高的作为预测分类的结果

样本数据集：0、1、2、3。分别是黑夜、激光、CXK、山水
以上有三种方法，参考其他博主。

import datetime
starttime=datetime.datetime.now()

import numpy as np
import os
import cv2 as cv
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix,classification_report
from sklearn.neighbors import KNeighborsClassifier
#from numpy import *


# 1 导入数据

X=[]
Y=[]

for i in range(0, 4):
    # 遍历文件夹，读取图片
    for f in os.listdir("D:/testimage/test/%s" % i):
        # 获取图像名称
        img = cv.imread("D:/testimage/test/" + str(i) + "/" + str(f))
        image = cv.resize(img, (256, 256), interpolation=cv.INTER_CUBIC)
        image=cv.cvtColor(image,cv.COLOR_BGR2GRAY)
        hist = cv.calcHist([image], [0], None, [256], [0.0, 256.0])
        X.append(((hist / 255).flatten()))
        Y.append(i)

X = np.array(X)
Y = np.array(Y)

#切分训练集和测试集
x_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.3,random_state=1)


class KNN:
    def __init__(self, train_data, train_label, test_data):
        self.train_data = train_data
        self.train_label = train_label
        self.test_data = test_data

    def knn_classify(self):
        num_train = (self.train_data).shape[0]
        num_test = (self.test_data).shape[0]
        labels = []
        for i in range(num_test):
            y = []
            for j in range(num_train):
                dis = np.sum(np.square((self.train_data)[j] - (self.test_data)[i]))
                y.append(dis)
            labels.append(self.train_label[y.index(min(y))])
        labels = np.array(labels)
        return labels


knn = KNN(x_train, y_train, x_test)
predictions_labels = knn.knn_classify()
print(confusion_matrix(y_test, predictions_labels))
print(classification_report(y_test, predictions_labels))
endtime = datetime.datetime.now()
print(endtime - starttime)


#方法2 用KNN集成函数包
clf0 = KNeighborsClassifier(n_neighbors=10).fit(x_train, y_train)
predictions0 = clf0.predict(x_test)
print(confusion_matrix(y_test, predictions0))
print (classification_report(y_test, predictions0))

#方法3 数学原理方法
'''
def KNN_Classify(newInput, dataSet, labels, k):
    numSamples = dataSet.shape[0]  # shape[0]表示行数
    # tile(A, reps): 构造一个矩阵，通过A重复reps次得到
    # the following copy numSamples rows for dataSet
    diff = np.tile(newInput, (numSamples, 1)) - dataSet  # 按元素求差值
    squaredDiff = diff ** 2  # 将差值平方
    squaredDist = np.sum(squaredDiff, axis=1)  # 按行累加
    distance = squaredDist ** 0.5  # 将差值平方和求开方，即得距离

    # # step 2: 对距离排序
    # argsort() 返回排序后的索引值
    sortedDistIndices = np.argsort(distance)
    classCount = {}  # define a dictionary (can be append element)
    for i in range(k):
        # # step 3: 选择k个最近邻
        voteLabel = labels[sortedDistIndices[i]]

        # # step 4: 计算k个最近邻中各类别出现的次数
        # when the key voteLabel is not in dictionary classCount, get()
        # will return 0
        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1

    # # step 5: 返回出现次数最多的类别标签
    maxCount = 0
    for key, value in classCount.items():
        if value > maxCount:
            maxCount = value
            maxIndex = key
    return maxIndex


predictions = []
for i in range(x_test.shape[0]):
    predictions_labes = KNN_Classify(x_test[i], x_train, y_train, 10)
    predictions.append(predictions_labes)
print(confusion_matrix(y_test, predictions))
# 打印预测结果混淆矩阵
print(classification_report(y_test, predictions))
# 打印精度、召回率、FI结果
endtime = datetime.datetime.now()
print(endtime - starttime)
'''

由于样本很相似，所以准确率很高，样本的采集来源于视频帧率截取。

参考文献：[1]：机器学习之KNN算法实现图像分类
[2]：[Python图像处理] 二十六.图像分类原理及基于KNN、朴素贝叶斯算法的图像分类案例